Testing Stability of Regression Discontinuity Models∗

Regression discontinuity (RD) models are commonly used to nonparametrically identify and estimate a local average treatment e ect. Dong and Lewbel (2015) show how a derivative of this e ect, called TED (Treatment E ect Derivative) can be estimated. We argue here that TED should be employed in most RD applications, as a way to assess the stability and hence external validity of RD estimates. Closely related to TED, we de ne the Complier Probability Derivative (CPD). Just as TED measures stability of the treatment e ect, the CPD measures stability of the complier population in fuzzy designs. TED and CPD are numerically trivial to estimate. We provide relevant Stata code, and apply it to some real data sets. JEL Codes: C21, C25